Time travel Review We discussed motivations for human-in-the-loop: (1) Approval - We can interrupt our agent, surface state to a user, and allow the user to accept an action (2) Debugging - We can rewind the graph to reproduce or avoid issues (3) Editing - You can modify the state We showed how breakpoints can stop the graph at specific nodes or allow the graph to dynamically interrupt itself. Then we showed how to proceed with human approval or directly edit the graph state with human feedback. Goals Now, let's show how LangGraph supports debugging by viewing, re-playing, and even forking from past states. We call this time travel.
Autonomy
Semi-autonomous
Sandbox-aware
No declared sandbox guidance
Network access
Unspecified
Filesystem access
Unspecified
Permissions declared
Not declared
Pattern
Autonomous loop
Models
gpt-4oclaude-3-5-sonnetgpt-3.5-turbo